Citations

Background: Severe adolescent idiopathic scoliosis (AIS) can be treated with instrumented fusion, but the number of anchors needed for optimal correction is controversial. Methods: We conducted a multicenter, randomized study that included patients undergoing spinal fusion for single thoracic curves between 45° and 65°, the most common form of operatively treated AIS. Of the 211 patients randomized, 108 were assigned to a high-density screw pattern and 103, to a low-density screw pattern. Surgeons were instructed to use ≥1.8 implants per spinal level fused for patients in the high-implant-density group or ≤1.4 implants per spinal level fused for patients in the low-implant-density group. The primary outcome measure was the percent correction of the coronal curve at the 2-year follow-up. The power analysis for this trial required 174 patients to show equivalence, defined as a 95% confidence interval (CI) within a ±10% correction margin with a probability of 90%. Results: In the intention-to-treat analysis, the mean percent correction of the coronal curve was equivalent between the high-density and low-density groups at the 2-year follow-up (67.6% versus 65.7%; difference, −1.9% [95% CI: −6.1%, 2.2%]). In the per-protocol cohorts, the mean percent correction of the coronal curve was also equivalent between the 2 groups at the 2-year follow-up (65.0% versus 66.1%; difference, 1.1% [95% CI: −3.0%, 5.2%]). A total of 6 patients in the low-density group and 5 patients in the high-density group required reoperation (p = 1.0). Conclusions: In the setting of spinal fusion for primary thoracic AIS curves between 45° and 65°, the percent coronal curve correction obtained with use of a low-implant-density construct and that obtained with use of a high-implant-density construct were equivalent. Level of Evidence: Therapeutic Level I . See Instructions for Authors for a complete description of levels of evidence.

Abstract Clinical management of IDH wildtype glioblastoma (GBM) and tumefactive multiple sclerosis (tMS) is drastically different. GBM requires maximal safe resection followed by chemoradiation, while tMS outcome is worsened by surgery and radiotherapy. Misdiagnosis of brain lesions may expose patients to unnecessary anxiety, surgery, or radiotherapy. Noninvasive methods to help with accurate diagnosis of tumor and non-tumor etiologies are needed. tMS subjects were identified by the Mayo Clinic Center for Multiple Sclerosis and Autoimmune Neurology (CMSAN). GBM subjects were matched to tMS by age at diagnosis, index MRI date, and sex. Inclusion criteria included one cm minimal lesion size and pre-operative post-contrast T1 and T2 images available for analysis. To identify potential experimental design bias, MRI technology and clinical characteristics were compared across groups. A 3D-DenseNet121 was used to develop a classification model using prespecified parameters: 600 epochs, batch size 16, learning rate 10-3, cross entropy loss, and AdamW optimizer. The stopping rule was defined as three sequential epoch cross entropy loss < 0.02. Five-fold cross validation (CV) was utilized to obtain an unbiased estimate of predictive performance (overfitting) and sensitivity of the 3D-DenseNet121 algorithm was evaluated. 224 subjects (114 GBM, 110 tMS) were analyzed: 40% male, median age 46. After one round of CV, the average unbiased estimate of sensitivity and specificity for predicting GBM from the final classification model was 0.86 and 0.73, respectively. To assess the reproducibility of the deep learning algorithm (3D-DenseNet121), the exact same CV folds were rerun resulting in average sensitivity and specificity of 0.82 and 0.75, respectively. Obtaining unbiased estimates of model performance using internal validation is critical before evaluating a final model on an external dataset. Understanding sensitivity of a deep learning algorithm is important for model validity. Differentiation of GBM and tMS appears reasonable with MRI; external validation is in progress.

Abstract INTRODUCTION Prior to 2021, (classic) glioblastoma (GBM) required absence of IDH mutation and histologic features of hypercellularity, nuclear atypia, microvascular proliferation (MVP), and necrosis. Absence of histologic features can be a result of undersampling, with molecular, radiologic, and clinical features consistent with GBM. Accordingly, WHO 2021 defined molecular glioblastoma as diffuse glioma IDHwt, H3wt, with one or more of MVP, necrosis, TERT promoter mutation, EGFR gene amplification (EGFRamp), and/or +7/−10. We hypothesized that there is clinical and radiographic heterogeneity among tumors defined as molecular GBM. METHODS We identified 121 patients that met the criteria for molecular GBM. 121 Classic GBM, defined as IDHwt with hypercellularity, MVP or necrosis, were matched to molecular GBM cases by age, sex, and diagnosis date. All cases were reviewed for relevant histologic features and molecular features. Examined clinical variables included: first symptom, time from first symptom to date of pathological diagnosis, date of first MRI, tumor location, radiographic features of enhancement, diffusion or mass effect, time to progression and overall survival. Clinical, radiologic, and molecular features were compared between classic and molecular GBM. RESULTS Currently,160 cases have been reviewed. Preliminary results show that there is a longer time from first symptom to diagnosis for molecular GBM. Molecular GBM is significantly more likely to be discovered coincidentally, and without enhancement or radiographic necrosis. Classic GBM is significantly more likely to present with focal neurologic deficit as first symptom, regional mass effect on index imaging and have monosomy 10. CONCLUSION While pathologic undersampling accounts for a significant proportion of molecular GBM, our data suggest that there are significant clinical, radiographic, and outcome differences between classical and molecular GBM. Final analysis of the entire cohort will help better define this clinical spectrum.

Abstract There have been several attempts to predict the MGMT promoter methylation status of gliomas using deep learning (DL), with mixed results. These studies did not account for IDH mutation status and did not utilize a uniform methylation assay, introducing potential confounders in the experimental design. We assessed the performance of DL applied to brain MRI to predict the MGMT promoter methylation status of IDH-wildtype gliomas tested with a standardized assay. We included 539 IDH-wildtype gliomas tested with real-time methylation-specific PCR from 2017-2022; 205 (38%) were MGMT promoter methylated. The assay targets 8 downstream MGMT CpG sites using ACTB as control; methylation status is determined based on the difference of PCR crossing-point values: methylated if difference < 5, unmethylated if difference > 7, indeterminate otherwise. We used post-contrast T1 and T2 MRIs as inputs for our models trained using stratified 5-fold cross-validation, 400 epochs, batch size of 16, a learning rate scheduler starting at 10-3, weighted binary cross-entropy loss, and AdamW optimizer. We repeated the experiments using two 3D DL architectures (DenseNet121 and EfficientNetB0) and two image preprocessing pipelines: the BraTS protocol and one that uses padding instead of registration to an MRI atlas, keeping constant other experimental variables. For Densenet121, the best cross-validation AUROCC and F1-score (median, median absolute deviation) were 0.67 (0.06), 0.59 (0.02) using the BraTS protocol, and 0.67 (0.06), 0.58 (0.01) using padding. For EfficientNetB0, were 0.67 (0.02), 0.66 (0.01) using the BraTS protocol and 0.67 (0.01), 0.68 (0.01) using padding. Our findings suggest that it is unlikely that DL models trained on brain MRI can predict the MGMT promoter methylation of IDH-wildtype gliomas. Importantly, our study is the first to focus on an IDH-wildtype adult diffuse glioma cohort tested with a single, standardized MGMT methylation assay, eliminating the variability introduced by different assays and IDH status.

Abstract Incomplete MRI exams reduce the possibility of applying AI models. We previously trained two generative adversarial networks (GANs) on 135 subjects from the BraTS-2017 dataset to generate T1 from post-contrast T1 and FLAIR from T2 sequences (baseline models). To test the impact of the training set size, here, we trained the same models using 1251 subjects from the BraTS-2021 dataset. We used the same architecture and hyperparameters from the baseline models: batch size of 1, learning rate 2x10-4, Adam optimizer, cross-entropy and L1-loss. We trained two versions of the updated models: one stopped at an early checkpoint (early models) and one after 50 epochs (late models). We tested all models on institutional MRIs from 487 IDH-wt gliomas. Synthetic MRIs were compared to the originals using the structural-similarity-index (SSI) and MSE. We simulated scenarios where either the T1, FLAIR, or both were missing and used their synthetic version as inputs of a segmentation model. We compared the segmentations using the dice score (DSC) and used Friedman and Dunn’s test to compare the scores and correct for multiple comparisons. Median SSI for the T1 were 0.957, 0.947, 0.947, and median MSE were 0.006, 0.014, 0.008 for the baseline, early, and late models. For the FLAIR, median SSI were 0.924, 0.908, 0.915, and median MSE were 0.016, 0.016, 0.019 for the baseline, early, and late models. The DSC ranges for the baseline and updated models were (0.655 - 0.953), (0.420 - 0.952), and (0.610 - 0.952). The baseline and late models showed no statistically significant differences in DSC, but both performed significantly better than the early models. We show that GANs trained to synthesize brain MRIs on a small cohort perform similarly to those trained on an x10-larger cohort, making them a viable option for rare diseases or institutions with limited resources.

OBJECTIVE Arginine vasopressin deficiency (AVD) following neurosurgical procedures for pituitary disorders is common and can delay discharge. Copeptin, a stable surrogate marker of arginine vasopressin, may predict postoperative AVD. The authors’ aim was to assess the optimal postoperative sampling time and cut-point concentration of copeptin to predict the development of postsurgical AVD. METHODS Adults without preexisting AVD who were undergoing surgery for a pituitary lesion between February 2020 and April 2022 were eligible for study inclusion. Two samples were drawn from each patient postoperatively to assess the copeptin concentration using an immunofluorescent assay. Samples were denoted as "early" (within 6 hours of extubation) or "postoperative day 1" (POD1; within 10–30 hours of extubation). Patients were evaluated for the development of AVD. RESULTS One hundred ninety-two patients (54.2% female) with a median age of 54.5 years (IQR 39.8–67.0 years) were included in the study. The median copeptin concentration at both time points was significantly lower in those with AVD (transient or permanent; n = 22, 11.5%) than in those without (early: 4.9 vs 18.7 pmol/L, p < 0.001; POD1: 3.4 vs 4.9 pmol/L, p < 0.001) but did not differ in those who developed transient versus permanent AVD. The optimal copeptin cut point for the prediction of AVD was < 8.5 pmol/L for early samples (sensitivity 0.70, specificity 0.80, positive predictive value [PPV] 0.29, negative predictive value [NPV] 0.96) and < 4.3 pmol/L for POD1 samples (sensitivity 0.82, specificity 0.63, PPV 0.22, NPV 0.96). In early samples, a copeptin cutoff of 22.9 pmol/L increased the sensitivity for the detection of AVD to 95% with an NPV of 99%. The proportion of patients who had AVD was higher (60.0% vs 8.8%, p < 0.001) and the copeptin concentration lower (early: 4.3 vs 17.0 pmol/L, p < 0.001; POD1: 2.7 vs 4.9 pmol/L, p < 0.001) among those who had undergone surgery for a craniopharyngeal duct pathology versus a pituitary adenoma. Although copeptin was lower in patients with persistent Cushing’s disease than in those in remission, the difference did not reach statistical significance (early p = 0.11, POD1 p = 0.52). Furthermore, the copeptin concentration could not predict the development of syndrome of inappropriate secretion of antidiuretic hormone. Patients without AVD who had received stress dose steroids intraoperatively had lower median early copeptin (11.7 vs 19.1 pmol/L, p = 0.027). CONCLUSIONS In early postoperative copeptin samples, the optimal copeptin cut point for AVD diagnosis was < 8.5 pmol/L, and a level > 22.9 pmol/L had predicative utility in excluding AVD. Caution should be used when interpreting copeptin results, as patients administered glucocorticoids intraoperatively without AVD had lower median copeptin concentrations.

Abstract Disclosure: J. Saini: None. R. Gregg Garcia: None. J. Herndon: None. D.Z. Erickson: None. L. Gruber: None. I. Bancos: None. Context: Overnight metyrapone test (OMT) is a dynamic test used to diagnose secondary adrenal insufficiency (SAI). However, it is uncommonly used and the data on the OMT indications and performance are scarce. We aimed to characterize the indications, performance, and safety of outpatient OMT. Methods: Single center retrospective study in adults with OMT between April 1st, 2018 -July 31st, 2022. We evaluated three post-OMT cutoffs diagnostic of SAI: 1) 11-deoxycortisol ≤7 mcg/dL (11D≤7); 2) 11-deoxycortisol ≤10 mcg/dL (11D≤10), or 3) sum of cortisol and 11-deoxycortisol ≤15 mcg/dL (sum≤15), in comparison to pre-test probability and reference standard, defined as clinician-made diagnosis of SAI. When available, OMT-based SAI diagnosis was compared to results from the cosyntropin stimulation test (CST). Results: OMT was performed in 109 patients (76, 70% women) at a median age of 48 (IQR, 37-59) years. Pre-test probability for SAI was high in 13 (12%), moderate in 46 (43%), and low in 49 (45%) patients. Indications for OMT included evaluation of symptoms without clear SAI risk factors (38, 35%), suspected SAI due to chronic opioid use (25, 23%), pituitary pathology/therapies (25, 23%), exogenous glucocorticoid use (8, 7%), other (13, 12%). Overnight metyrapone was administered at a median dose of 2500 (IQR, 2125-3000). Adverse events were reported by 9 (8%) patients and were mild (nausea, fatigue) except for 1 patient who had to be hospitalized. The final diagnosis of SAI was made in 25 (48%) patients: 92%, 52%, and 12% of patients with high, moderate, and low pre-test probability. When compared to the clinician-made SAI diagnosis, OMT-based diagnosis of SAI was made in 60% of patients using the 11D≤7 cutoff, and in 81% of patients using the other cutoffs (11D≤10 or sum≤15). In 50 patients with concomitant CST, the final diagnosis of SAI was made in 23 (46%) patients, despite the normal CST results (post-cosyntropin peak cortisol ≥18 mcg/dL) in 12/23 patients. In patients with post-cosyntropin peak cortisol ≥18 mcg/dL, OMT was abnormal in 14% of patients (using post-OMT cutoff 11D≤7), 29% of patients (based on cutoff 11D≤10), and in 30% of patients (based on sum≤15). Conclusions: Outpatient OMT is well tolerated and was mostly used in patients with low/moderate pre-test probability for SAI. In patients with normal CST, OMT may diagnose SAI in additional 30% of patients, especially if the pre-test probability is high. Post-OMT sum of 11-deoxycortisol and cortisol &lt;15 mcg/dL performs well in diagnosing SAI while allowing confirmation of adequate cortisol suppression. Presentation: Saturday, June 17, 2023

Abstract Disclosure: D.Z. Erickson: None. D. Donegan: None. J. Van Gompel: None. J. Atkinson: None. M. Link: None. F. Meyer: None. M. Peris-Celda: None. G. Spears: None. J. Bornhorst: None. M. Hoplin: None. Dysnatremias are common after neurosurgical procedures. Depending on the cohort assessed, transient arginine vasopressin deficiency (AVD) following neurological procedures is seen in up to 46% of patients which can delay discharge. Copeptin (COPEP), a stable surrogate marker of arginine vasopressin, has demonstrated utility in the prediction of postoperative AVD, however COPEP cutoff and sample timing has varied. Aim: To assess the optimal sampling time and cut point concentration of COPEP to predict the development of post-surgical AVD. Method: Adults who had transsphenoidal surgery (TSS) for a sellar or suprasellar mass between February 2020 and April 2022 without pre-existing AVD were prospectively enrolled if agreeable. Two COPEP samples (immunofluorescent assay on B.R.A.H.M.S Kryptor Compact PLUS) included “early” sample 1-6 hours following extubation, and another post-op day 1 (POD1, 10-30 hours of extubation). Patients were assessed for the development of AVD; defined as new onset hypotonic (&lt; 295 mmol/kg) polyuria (&gt;50 ml/kg/d) without other causes. Patient demographics and tumor characteristics were collected. Results: 192 patients (median age 54.5 (39.8-67.0) years with 54.2% female) were included. Surgical indications included non-functioning pituitary adenoma (N=101), functioning pituitary adenoma (N= 78), disorders or the craniopharyngeal duct (N=10) and other (N=3). Median COPEP levels were associated with age, but not sex. Median COPEP levels were significantly lower at both time points in patients who developed AVD (N=20, 10.4%) vs those who did not, (early: 4.9 vs 18.7 pmol/L, P= &lt;0.001; POD1: 3.35 vs 4.9 pmol/L, P=&lt;0.001). Change in median COPEP level between the 2 sample times was lower in those who developed AVD -1.8 pmol/L vs who did not -12.6 pmol/L (P&lt;0.001). ROC curve analysis of early COPEP indicated that a level &gt;20.3 pmol/L had a negative predictive value (NPV) of 97% whereas POD1 level &gt;6.7 pmolL had a NPV of 96%. In univariate logistic analysis, lower early COPEP was associated with higher risk of AVD (OR=0.34, CI 0.26 -0.62, p=0.008), with an optimal cut point of 8.5 pmol/L. A similar association was seen for POD1 COPEP (OR=0.19, CI 0.07- 0.53, p= 0.002), which had an optimal cut point of 4.3 pmol/L. In patients with disorders of the craniopharyngeal system vs those who had TSS for other reasons, AVD was more common (60% vs 9%, P&lt;0.001) and median COPEP levels were lower at both time points. Those without AVD who received stress dose steroids intraoperatively had lower median early COPEP (11.7 vs 19.1 pmol/L, P=0.27). Conclusion: In early samples taken following extubation, the optimal COPEP cut point for AVD diagnosis was 8.5 pmol/L and a level of &gt;20.3 pmol/L has predicative utility in excluding AVD. However, caution should be used in patients who are administered glucocorticoids intra-operatively as this was associated with a lower median COPEP level. Presentation: Thursday, June 15, 2023

Background: Although pitch count and rest guidelines have been promoted for youth and adolescent baseball players for nearly 2 decades, compliance with guidelines remains poorly understood. Purpose/Hypothesis: The purpose of this study was to determine the frequency of compliance with Major League Baseball (MLB) Pitch Smart guidelines as well as the association between compliance and range of motion (ROM), strength, velocity, injury, and pitcher utilization. It was hypothesized that pitchers in violation of current recommendations would have increased strength, velocity, and injury. Study Design: Case-control study; Level of evidence, 3. Methods: This was a prospective, multicenter study of 115 high school pitchers throughout the United States. Pitchers were surveyed about their compliance with current off-season, rest-related guidelines, and history of injury. During the preseason, pitchers underwent standardized physical examinations, and pitch velocity was measured. Pitch counts were collected during the baseball season that followed. Dynamometer strength testing of shoulder forward flexion, and external rotation as well as grip strength was recorded. We compared pitchers who were compliant with recommendations with those who were noncompliant using Student t and Mann-Whitney U tests. Results: Based on preseason data, 84% of pitchers had violated current Pitch Smart guidelines. During the season, 14% had at least 1 violation of the Pitch Smart guidelines. Across both the preseason survey and in-season pitch counts, 89% of players had at least 1 violation of the Pitch Smart guidelines. While there were no significant differences in ROM or strength, the noncompliant group had higher maximum pitch velocity than the compliant group (74 ± 8 vs 69 ± 5 mph [119 ± 13 vs 111 ± 8 kph], respectively; P = .009). Players’ self-reported velocity differed significantly from the direct measurement, for both peak velocity (80 ± 6 vs 73 ± 8 mph [129 ± 9 vs 117 ± 13 kph], respectively; P < .001) and mean velocity (73 ± 8 vs 53 ± 27 mph [117 ± 13 vs 85 ± 43 kph], respectively; P < .001). Conclusion: Most high school pitchers were not fully compliant with current Pitch Smart guidelines, and they tended to overestimate their peak velocity by 7 mph (11 kph). Pitchers who threw with greater velocity were at higher risk for violating Pitch Smart recommendations.